About me (Registered since 23/10/2025)

Senior AI Researcher specializing in Computer Vision and Automatic Speech Recognition
(ASR), with growing expertise in Large Language Models (LLMs) and Generative AI.
Experienced in developing AI models for medical imaging and speech processing in
low-resource Indian languages. Skilled in leading research initiatives and coordinating with
cross-functional teams in fast-paced startup environments.

Skills

Tech Skills

Portfolio

Education

Key Skills and Competencies

I bring a strong blend of technical expertise and leadership experience in AI and Data Science, with proficiency in Python and Shell scripting and hands-on experience across deep learning frameworks such as PyTorch, Keras-TensorFlow, and Scikit-learn. My core competencies span Computer Vision, including image preprocessing, classification, semantic and instance segmentation, object detection, OCR, and dataset creation—including synthetic data generation. I have led teams of data scientists and AI researchers on computer vision projects in arthroscopic surgery, delivering models for classification, object detection, and segmentation. In speech processing, I have developed ASR models for Indian languages like Assamese, Mizo, Bengali, and Hindi, leading government-sponsored projects and creating custom speech databases using IVRS. I am also expanding my expertise in NLP and LLMs, including LangChain, Hugging Face, RAG systems, and fine-tuning frameworks. My experience extends to cloud platforms (GCP, AWS, Azure), MLOps & deployment (Docker, MLflow, FastAPI, Streamlit), and databases (MySQL, MongoDB), along with proficiency in data labeling tools such as V7 Darwin, Encord, Roboflow, and Labelbox. Additionally, I have applied AI to specialized projects like image clustering and gait analysis, showcasing a balance of research, development, and practical deployment skills.

Work Experience

Languages

English
Professional
Bengali
Professional
Hindi
Professional
Assamese
Professional